© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 51904
    Prev
    Next
    INDEX
    Explanations

    convert to string or data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uman
    -0.08
    çĿĢä¸Ģ
    -0.07
    ays
    -0.07
    illons
    -0.06
    {}",
    -0.06
    ouch
    -0.06
    èŀ
    -0.06
    antz
    -0.06
    åIJİåı¯
    -0.06
    aru
    -0.06
    POSITIVE LOGITS
    antil
    0.08
    ehme
    0.08
    äºīåģļ
    0.08
    kak
    0.07
    ãģ¾ãģĦ
    0.07
    anni
    0.07
    Ñıн
    0.07
    éĢļãĤĬãģ«
    0.07
    åĭĺ
    0.07
    sang
    0.07
    Activations Density 0.006%

    No Known Activations